Merge branch 'master' of https://github.com/tqchen/xgboost

R-package/R/utils.R

@@ -52,7 +52,7 @@ xgb.Booster <- function(params = list(), cachelist = list(), modelfile = NULL) {
   if (length(params) != 0) {
     for (i in 1:length(params)) {
       p <- params[i]
-      .Call("XGBoosterSetParam_R", handle, names(p), as.character(p), 
+      .Call("XGBoosterSetParam_R", handle, gsub("\\.", "_", names(p)), as.character(p),
             PACKAGE = "xgboost")
     }
   }

R-package/R/xgb.cv.R

@@ -20,7 +20,7 @@
 #' @param nrounds the max number of iterations
 #' @param nfold number of folds used
 #' @param label option field, when data is Matrix
-#' @param showd boolean, whether show standard deviation of cross validation
+#' @param showsd boolean, whether show standard deviation of cross validation
 #' @param metrics, list of evaluation metrics to be used in corss validation,
 #'   when it is not specified, the evaluation metric is chosen according to objective function.
 #'   Possible options are:
@@ -77,5 +77,5 @@ xgb.cv <- function(params=list(), data, nrounds, nfold, label = NULL,
     history <- append(history, ret)
     cat(paste(ret, "\n", sep=""))
   }
-  return (history)
+  return (TRUE)
 }

R-package/README.md

@@ -17,5 +17,5 @@ install.packages('xgboost')
 
 ## Examples
 
-* Please visit [demo](https://github.com/tqchen/xgboost/blob/master/R-package/inst/examples/demo.R) for walk throughe example.
+* Please visit [walk through example](https://github.com/tqchen/xgboost/blob/master/R-package/demo).
 * See also the [example scripts](https://github.com/tqchen/xgboost/tree/master/demo/kaggle-higgs) for Kaggle Higgs Challenge, including [speedtest script](https://github.com/tqchen/xgboost/blob/master/demo/kaggle-higgs/speedtest.R) on this dataset.

R-package/demo/00Index

@@ -0,0 +1,6 @@
+basic_walkthrough               Basic feature walkthrough
+custom_objective                Cutomize loss function, and evaluation metric
+boost_from_prediction           Boosting from existing prediction
+predict_first_ntree             Predicting using first n trees
+generalized_linear_model        Generalized Linear Model
+cross_validation                Cross validation

R-package/demo/README.md

@@ -3,6 +3,6 @@ XGBoost R Feature Walkthrough
 * [Basic walkthrough of wrappers](basic_walkthrough.R) 
 * [Cutomize loss function, and evaluation metric](custom_objective.R)
 * [Boosting from existing prediction](boost_from_prediction.R)
-* [Predicting using first n trees](predict_first_ntree.py)
-* [Generalized Linear Model](generalized_linear_model.py)
-* [Cross validation](cross_validation.py)
+* [Predicting using first n trees](predict_first_ntree.R)
+* [Generalized Linear Model](generalized_linear_model.R)
+* [Cross validation](cross_validation.R)

R-package/demo/basic_walkthrough.R

@@ -4,49 +4,49 @@ require(methods)
 # In this example, we are aiming to predict whether a mushroom can be eated
 data(agaricus.train, package='xgboost')
 data(agaricus.test, package='xgboost')
-dtrain <- agaricus.train
-dtest <- agaricus.test
+train <- agaricus.train
+test <- agaricus.test
 # the loaded data is stored in sparseMatrix, and label is a numeric vector in {0,1}
-class(dtrain$label)
-class(dtrain$data)
+class(train$label)
+class(train$data)
 
 #-------------Basic Training using XGBoost-----------------
 # this is the basic usage of xgboost you can put matrix in data field
 # note: we are puting in sparse matrix here, xgboost naturally handles sparse input
 # use sparse matrix when your feature is sparse(e.g. when you using one-hot encoding vector)
 print("training xgboost with sparseMatrix")
-bst <- xgboost(data = dtrain$data, label = dtrain$label, max_depth = 2, eta = 1, nround = 2,
+bst <- xgboost(data = train$data, label = train$label, max.depth = 2, eta = 1, nround = 2,
                objective = "binary:logistic")
 # alternatively, you can put in dense matrix, i.e. basic R-matrix
 print("training xgboost with Matrix")
-bst <- xgboost(data = as.matrix(dtrain$data), label = dtrain$label, max_depth = 2, eta = 1, nround = 2,
+bst <- xgboost(data = as.matrix(train$data), label = train$label, max.depth = 2, eta = 1, nround = 2,
                objective = "binary:logistic")
 
 # you can also put in xgb.DMatrix object, stores label, data and other meta datas needed for advanced features
 print("training xgboost with xgb.DMatrix")
-dmat <- xgb.DMatrix(data = dtrain$data, label = dtrain$label)
-bst <- xgboost(data = dmat, max_depth = 2, eta = 1, nround = 2, objective = "binary:logistic")
+dtrain <- xgb.DMatrix(data = train$data, label = train$label)
+bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nround = 2, objective = "binary:logistic")
 
 # Verbose = 0,1,2
 print ('train xgboost with verbose 0, no message')
-bst <- xgboost(data = dmat, max_depth = 2, eta = 1, nround = 2,
+bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nround = 2,
                objective = "binary:logistic", verbose = 0)
 print ('train xgboost with verbose 1, print evaluation metric')
-bst <- xgboost(data = dmat, max_depth = 2, eta = 1, nround = 2,
+bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nround = 2,
                objective = "binary:logistic", verbose = 1)
 print ('train xgboost with verbose 2, also print information about tree')
-bst <- xgboost(data = dmat, max_depth = 2, eta = 1, nround = 2,
+bst <- xgboost(data = dtrain, max.depth = 2, eta = 1, nround = 2,
                objective = "binary:logistic", verbose = 2)
 
 # you can also specify data as file path to a LibSVM format input
 # since we do not have this file with us, the following line is just for illustration
-# bst <- xgboost(data = 'agaricus.train.svm', max_depth = 2, eta = 1, nround = 2,objective = "binary:logistic")
+# bst <- xgboost(data = 'agaricus.train.svm', max.depth = 2, eta = 1, nround = 2,objective = "binary:logistic")
 
 #--------------------basic prediction using xgboost--------------
 # you can do prediction using the following line
 # you can put in Matrix, sparseMatrix, or xgb.DMatrix 
-pred <- predict(bst, dtest$data)
-err <- as.numeric(sum(as.integer(pred > 0.5) != dtest$label))/length(dtest$label)
+pred <- predict(bst, test$data)
+err <- mean(as.numeric(pred > 0.5) != test$label)
 print(paste("test-error=", err))
 
 #-------------------save and load models-------------------------
@@ -54,33 +54,33 @@ print(paste("test-error=", err))
 xgb.save(bst, "xgboost.model")
 # load binary model to R
 bst2 <- xgb.load("xgboost.model")
-pred2 <- predict(bst2, dtest$data)
+pred2 <- predict(bst2, test$data)
 # pred2 should be identical to pred
 print(paste("sum(abs(pred2-pred))=", sum(abs(pred2-pred))))
 
 #----------------Advanced features --------------
 # to use advanced features, we need to put data in xgb.DMatrix
-dtrain <- xgb.DMatrix(data = dtrain$data, label=dtrain$label)
-dtest <- xgb.DMatrix(data = dtest$data, label=dtest$label)
+dtrain <- xgb.DMatrix(data = train$data, label=train$label)
+dtest <- xgb.DMatrix(data = test$data, label=test$label)
 #---------------Using watchlist----------------
 # watchlist is a list of xgb.DMatrix, each of them tagged with name
 watchlist <- list(train=dtrain, test=dtest)
 # to train with watchlist, use xgb.train, which contains more advanced features
 # watchlist allows us to monitor the evaluation result on all data in the list 
 print ('train xgboost using xgb.train with watchlist')
-bst <- xgb.train(data=dtrain, "max_depth"=2, eta=1, nround=2, watchlist=watchlist,
+bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nround=2, watchlist=watchlist,
                  objective = "binary:logistic")
 # we can change evaluation metrics, or use multiple evaluation metrics
 print ('train xgboost using xgb.train with watchlist, watch logloss and error')
-bst <- xgb.train(data=dtrain, "max_depth"=2, eta=1, nround=2, watchlist=watchlist,
-                 "eval_metric" = "error", "eval_metric" = "logloss",
+bst <- xgb.train(data=dtrain, max.depth=2, eta=1, nround=2, watchlist=watchlist,
+                 eval.metric = "error", eval.metric = "logloss",
                  objective = "binary:logistic")
 
 # xgb.DMatrix can also be saved using xgb.DMatrix.save
 xgb.DMatrix.save(dtrain, "dtrain.buffer")
 # to load it in, simply call xgb.DMatrix
 dtrain2 <- xgb.DMatrix("dtrain.buffer")
-bst <- xgb.train(data=dtrain2, "max_depth"=2, eta=1, nround=2, watchlist=watchlist,
+bst <- xgb.train(data=dtrain2, max.depth=2, eta=1, nround=2, watchlist=watchlist,
                  objective = "binary:logistic")
 # information can be extracted from xgb.DMatrix using getinfo
 label = getinfo(dtest, "label")

R-package/demo/cross_validation.R

@@ -0,0 +1,47 @@
+require(xgboost)
+# load in the agaricus dataset
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
+dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
+
+nround <- 2
+param <- list(max_depth=2,eta=1,silent=1,objective='binary:logistic')
+
+cat('running cross validation\n')
+# do cross validation, this will print result out as
+# [iteration]  metric_name:mean_value+std_value
+# std_value is standard deviation of the metric
+xgb.cv(param, dtrain, nround, nfold=5, metrics={'error'})
+
+cat('running cross validation, disable standard deviation display\n')
+# do cross validation, this will print result out as
+# [iteration]  metric_name:mean_value+std_value
+# std_value is standard deviation of the metric
+xgb.cv(param, dtrain, nround, nfold=5,
+       metrics={'error'}, , showsd = FALSE)
+
+###
+# you can also do cross validation with cutomized loss function
+# See custom_objective.R
+##
+print ('running cross validation, with cutomsized loss function')
+
+logregobj <- function(preds, dtrain) {
+  labels <- getinfo(dtrain, "label")
+  preds <- 1/(1 + exp(-preds))
+  grad <- preds - labels
+  hess <- preds * (1 - preds)
+  return(list(grad = grad, hess = hess))
+}
+evalerror <- function(preds, dtrain) {
+  labels <- getinfo(dtrain, "label")
+  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
+  return(list(metric = "error", value = err))
+}
+
+param <- list(max_depth=2,eta=1,silent=1)
+# train with customized objective
+xgb.cv(param, dtrain, nround, nfold = 5,
+       obj = logregobj, feval=evalerror)
+

R-package/demo/generalized_linear_model.R

@@ -0,0 +1,34 @@
+require(xgboost)
+# load in the agaricus dataset
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
+dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
+##
+#  this script demonstrate how to fit generalized linear model in xgboost
+#  basically, we are using linear model, instead of tree for our boosters
+#  you can fit a linear regression, or logistic regression model
+##
+
+# change booster to gblinear, so that we are fitting a linear model
+# alpha is the L1 regularizer 
+# lambda is the L2 regularizer
+# you can also set lambda_bias which is L2 regularizer on the bias term
+param <- list(objective = "binary:logistic", booster = "gblinear",
+              alpha = 0.0001, lambda = 1)
+
+# normally, you do not need to set eta (step_size)
+# XGBoost uses a parallel coordinate descent algorithm (shotgun), 
+# there could be affection on convergence with parallelization on certain cases
+# setting eta to be smaller value, e.g 0.5 can make the optimization more stable
+
+##
+# the rest of settings are the same
+##
+watchlist <- list(eval = dtest, train = dtrain)
+num_round <- 2
+bst <- xgb.train(param, dtrain, num_round, watchlist)
+ypred <- predict(bst, dtest)
+labels <- getinfo(dtest, 'label')
+cat('error of preds=', mean(as.numeric(ypred>0.5)!=labels),'\n')
+

R-package/demo/predict_first_ntree.R

@@ -1,27 +1,23 @@
 require(xgboost)
-
-data(agaricus.train)
-data(agaricus.test)
-
-trainX = agaricus.train$data
-trainY = agaricus.train$label
-testX = agaricus.test$data
-testY = agaricus.test$label
-
-dtrain <- xgb.DMatrix(trainX, label=trainY)
-dtest <- xgb.DMatrix(testX, label=testY)
-
+# load in the agaricus dataset
+data(agaricus.train, package='xgboost')
+data(agaricus.test, package='xgboost')
+dtrain <- xgb.DMatrix(agaricus.train$data, label = agaricus.train$label)
+dtest <- xgb.DMatrix(agaricus.test$data, label = agaricus.test$label)
 
 param <- list(max_depth=2,eta=1,silent=1,objective='binary:logistic')
 watchlist <- list(eval = dtest, train = dtrain)
-num_round = 2
-bst = xgb.train(param, dtrain, num_round, watchlist)
+nround = 2
 
+# training the model for two rounds
+bst = xgb.train(param, dtrain, nround, watchlist)
 cat('start testing prediction from first n trees\n')
 labels <- getinfo(dtest,'label')
+
+### predict using first 1 tree
 ypred1 = predict(bst, dtest, ntreelimit=1)
+# by default, we predict using all the trees
 ypred2 = predict(bst, dtest)
 
 cat('error of ypred1=', mean(as.numeric(ypred1>0.5)!=labels),'\n')
 cat('error of ypred2=', mean(as.numeric(ypred2>0.5)!=labels),'\n')
-

R-package/demo/runall.R

@@ -0,0 +1,8 @@
+# running all scripts in demo folder
+source('basic_walkthrough.R')
+source('custom_objective.R')
+source('boost_from_prediction.R')
+source('predict_first_ntree.R')
+source('generalized_linear_model.R')
+source('cross_validation.R')
+

demo/guide-R/README.md

@@ -1,3 +0,0 @@
-XGBoost R Feature Walkthrough
-====
-To be finished

demo/guide-R/basic_walkthrough.R

@@ -1,47 +0,0 @@
-require(xgboost)
-require(methods)
-data(agaricus.train)
-data(agaricus.test)
-
-# we use agaricus data as example dataset
-# we will show how to use xgboost to do binary classification here
-
-trainX = agaricus.train$data
-trainY = agaricus.train$label
-testX = agaricus.test$data
-testY = agaricus.test$label
-#-------------------------------------
-# this is the basic usage of xgboost
-# you can put sparse matrix in data field. this is helpful when your data is sparse
-# for example, when you use one-hot encoding for feature vectors
-bst <- xgboost(data = trainX, label = trainY, max_depth = 1, eta = 1, nround = 2,
-               objective = "binary:logistic")
-# alternatively, you can put dense matrix
-denseX <- as(trainX, "matrix")
-bst <- xgboost(data = denseX, label = trainY, max_depth = 1, eta = 1, nround = 2,
-               objective = "binary:logistic")
-
-# you can also specify data as file path to a LibSVM format input
-# since we do not have libsvm format file for iris, next line is only for illustration
-# bst <- xgboost(data = 'iris.svm', max_depth = 2, eta = 1, nround = 2, objective = "binary:logistic")
-
-dtrain <- xgb.DMatrix(trainX, label=trainY)
-dtest <- xgb.DMatrix(testX, label=testY)
-
-
-param <- list(max_depth=2,eta=1,silent=1,objective='binary:logistic')
-watchlist <- list(eval = dtest, train = dtrain)
-num_round <- 2
-bst <- xgb.train(param, dtrain, num_round, watchlist)
-preds <- predict(bst, dtest)
-labels <- getinfo(dtest,'label')
-cat('error=', mean(as.numeric(preds>0.5)!=labels),'\n')
-xgb.save(bst, 'xgb.model')
-xgb.dump(bst, 'dump.raw.txt')
-xgb.dump(bst, 'dump.nuce.txt','../data/featmap.txt')
-
-bst2 <- xgb.load('xgb.model')
-preds2 <- predict(bst2,dtest)
-stopifnot(sum((preds-preds2)^2)==0)
-
-############################ Test xgb.DMatrix with local file, sparse matrix and dense matrix in R.

demo/guide-R/boost_from_prediction.R

@@ -1,31 +0,0 @@
-require(xgboost)
-
-data(agaricus.train)
-data(agaricus.test)
-
-trainX = agaricus.train$data
-trainY = agaricus.train$label
-testX = agaricus.test$data
-testY = agaricus.test$label
-
-dtrain <- xgb.DMatrix(trainX, label=trainY)
-dtest <- xgb.DMatrix(testX, label=testY)
-
-
-watchlist <- list(eval = dtest, train = dtrain)
-print('start running example to start from a initial prediction\n')
-param <- list(max_depth=2,eta=1,silent=1,objective='binary:logistic')
-bst <- xgb.train( param, dtrain, 1, watchlist )
-
-ptrain <- predict(bst, dtrain, outputmargin=TRUE)
-ptest  <- predict(bst, dtest, outputmargin=TRUE)
-# dtrain.set_base_margin(ptrain)
-# dtest.set_base_margin(ptest)
-
-
-cat('this is result of running from initial prediction\n')
-bst <- xgb.train( param, dtrain, 1, watchlist )
-
-
-
-

demo/guide-R/cross_validation.R

@@ -1,75 +0,0 @@
-require(xgboost)
-
-data(agaricus.train)
-data(agaricus.test)
-
-trainX = agaricus.train$data
-trainY = agaricus.train$label
-testX = agaricus.test$data
-testY = agaricus.test$label
-
-dtrain <- xgb.DMatrix(trainX, label=trainY)
-dtest <- xgb.DMatrix(testX, label=testY)
-
-num_round <- 2
-param <- list(max_depth=2,eta=1,silent=1,objective='binary:logistic')
-
-cat('running cross validation\n')
-# do cross validation, this will print result out as
-# [iteration]  metric_name:mean_value+std_value
-# std_value is standard deviation of the metric
-xgb.cv(param, dtrain, num_round, nfold=5,
-       metrics={'error'}, seed = 0)
-
-cat('running cross validation, disable standard deviation display\n')
-# do cross validation, this will print result out as
-# [iteration]  metric_name:mean_value+std_value
-# std_value is standard deviation of the metric
-xgb.cv(param, dtrain, num_round, nfold=5,
-       metrics={'error'}, seed = 0, show_stdv = False)
-
-cat('running cross validation, with preprocessing function\n')
-# define the preprocessing function
-# used to return the preprocessed training, test data, and parameter
-# we can use this to do weight rescale, etc.
-# as a example, we try to set scale_pos_weight
-fpreproc <- function(dtrain, dtest, param){
-  label <- getinfo(dtrain, 'label')
-  ratio <- mean(label==0)
-  param <- append(param, list(scale_pos_weight = ratio))
-  return(list(dtrain=dtrain, dtest= dtest, param = param))
-}
-
-
-# do cross validation, for each fold
-# the dtrain, dtest, param will be passed into fpreproc
-# then the return value of fpreproc will be used to generate
-# results of that fold
-xgb.cv(param, dtrain, num_round, nfold=5,
-       metrics={'auc'}, seed = 0, fpreproc = fpreproc)
-
-###
-# you can also do cross validation with cutomized loss function
-# See custom_objective.py
-##
-print ('running cross validation, with cutomsized loss function')
-
-logregobj <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  preds <- 1/(1 + exp(-preds))
-  grad <- preds - labels
-  hess <- preds * (1 - preds)
-  return(list(grad = grad, hess = hess))
-}
-
-evalerror <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
-  return(list(metric = "error", value = err))
-}
-
-param <- list(max_depth=2,eta=1,silent=1)
-# train with customized objective
-xgb.cv(param, dtrain, num_round, nfold = 5, seed = 0,
-       obj = logregobj, feval=evalerror)
-

demo/guide-R/custom_objective.R

@@ -1,47 +0,0 @@
-require(xgboost)
-
-data(agaricus.train)
-data(agaricus.test)
-
-trainX = agaricus.train$data
-trainY = agaricus.train$label
-testX = agaricus.test$data
-testY = agaricus.test$label
-
-dtrain <- xgb.DMatrix(trainX, label=trainY)
-dtest <- xgb.DMatrix(testX, label=testY)
-
-# note: for customized objective function, we leave objective as default
-# note: what we are getting is margin value in prediction
-# you must know what you are doing
-param <- list(max_depth=2,eta=1,silent=1)
-watchlist <- list(eval = dtest, train = dtrain)
-num_round <- 2
-
-
-# user define objective function, given prediction, return gradient and second order gradient
-# this is loglikelihood loss
-logregobj <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  preds <- 1/(1 + exp(-preds))
-  grad <- preds - labels
-  hess <- preds * (1 - preds)
-  return(list(grad = grad, hess = hess))
-}
-
-# user defined evaluation function, return a pair metric_name, result
-# NOTE: when you do customized loss function, the default prediction value is margin
-# this may make buildin evalution metric not function properly
-# for example, we are doing logistic loss, the prediction is score before logistic transformation
-# the buildin evaluation error assumes input is after logistic transformation
-# Take this in mind when you use the customization, and maybe you need write customized evaluation function
-evalerror <- function(preds, dtrain) {
-  labels <- getinfo(dtrain, "label")
-  err <- as.numeric(sum(labels != (preds > 0)))/length(labels)
-  return(list(metric = "error", value = err))
-}
-
-
-# training with customized objective, we can also do step by step training
-# simply look at xgboost.py's implementation of train
-bst = xgb.train(param, dtrain, num_round, watchlist, logregobj, evalerror)

demo/guide-R/generalized_linear_model.R

@@ -1,32 +0,0 @@
-#!/usr/bin/python
-import sys
-sys.path.append('../../wrapper')
-import xgboost as xgb
-##
-#  this script demonstrate how to fit generalized linear model in xgboost
-#  basically, we are using linear model, instead of tree for our boosters
-##
-dtrain = xgb.DMatrix('../data/agaricus.txt.train')
-dtest = xgb.DMatrix('../data/agaricus.txt.test')
-# change booster to gblinear, so that we are fitting a linear model
-# alpha is the L1 regularizer 
-# lambda is the L2 regularizer
-# you can also set lambda_bias which is L2 regularizer on the bias term
-param = {'silent':1, 'objective':'binary:logistic', 'booster':'gblinear',
-         'alpha': 0.0001, 'lambda': 1 }
-
-# normally, you do not need to set eta (step_size)
-# XGBoost uses a parallel coordinate descent algorithm (shotgun), 
-# there could be affection on convergence with parallelization on certain cases
-# setting eta to be smaller value, e.g 0.5 can make the optimization more stable
-# param['eta'] = 1 
-
-##
-# the rest of settings are the same
-##
-watchlist  = [(dtest,'eval'), (dtrain,'train')]
-num_round = 4
-bst = xgb.train(param, dtrain, num_round, watchlist)
-preds = bst.predict(dtest)
-labels = dtest.get_label()
-print ('error=%f' % ( sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) /float(len(preds))))

demo/guide-R/runall.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-# todo 
-Rscript basic_walkthrough.R
-Rscript custom_objective.R
-Rscript boost_from_prediction.R